Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Person characteristics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Layers
    -0.07
    ٹ
    -0.06
    (properties
    -0.06
     bum
    -0.06
     interpersonal
    -0.06
    ex
    -0.06
     RAND
    -0.06
     interior
    -0.06
    Transform
    -0.06
    /_
    -0.06
    POSITIVE LOGITS
     LinearLayout
    0.07
     discourage
    0.07
    ROTO
    0.06
    );//
    0.06
    enegro
    0.06
    .").
    0.06
     tarz
    0.06
    etiyle
    0.06
    ……。
    0.06
    _BACKEND
    0.06
    Act Density 0.048%

    No Known Activations